{"id":"https://openalex.org/W4381735275","doi":"https://doi.org/10.1109/tcsvt.2023.3288205","title":"Transformer Driven Matching Selection Mechanism for Multi-Label Image Classification","display_name":"Transformer Driven Matching Selection Mechanism for Multi-Label Image Classification","publication_year":2023,"publication_date":"2023-06-23","ids":{"openalex":"https://openalex.org/W4381735275","doi":"https://doi.org/10.1109/tcsvt.2023.3288205"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2023.3288205","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3288205","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101696778","display_name":"Yanan Wu","orcid":"https://orcid.org/0000-0002-3301-6303"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanan Wu","raw_affiliation_strings":["Key Laboratory of Big Data and Artificial Intelligence in Transportation, Ministry of Education, and the School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3301-6303","affiliations":[{"raw_affiliation_string":"Key Laboratory of Big Data and Artificial Intelligence in Transportation, Ministry of Education, and the School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085406955","display_name":"Songhe Feng","orcid":"https://orcid.org/0000-0002-5922-9358"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songhe Feng","raw_affiliation_strings":["Key Laboratory of Big Data and Artificial Intelligence in Transportation, Ministry of Education, and the School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5922-9358","affiliations":[{"raw_affiliation_string":"Key Laboratory of Big Data and Artificial Intelligence in Transportation, Ministry of Education, and the School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082727135","display_name":"Gongpei Zhao","orcid":"https://orcid.org/0000-0003-2758-7502"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gongpei Zhao","raw_affiliation_strings":["Key Laboratory of Big Data and Artificial Intelligence in Transportation, Ministry of Education, and the School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Big Data and Artificial Intelligence in Transportation, Ministry of Education, and the School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033896100","display_name":"Yi Jin","orcid":"https://orcid.org/0000-0001-8408-3816"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Jin","raw_affiliation_strings":["Key Laboratory of Big Data and Artificial Intelligence in Transportation, Ministry of Education, and the School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8408-3816","affiliations":[{"raw_affiliation_string":"Key Laboratory of Big Data and Artificial Intelligence in Transportation, Ministry of Education, and the School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I21193070"],"apc_list":null,"apc_paid":null,"fwci":2.1554,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.88612008,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"34","issue":"2","first_page":"924","last_page":"937"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6262822151184082},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6107656955718994},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5729890465736389},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.45616844296455383},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.42153415083885193},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.4158411920070648},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.31988632678985596}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6262822151184082},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6107656955718994},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5729890465736389},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.45616844296455383},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42153415083885193},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.4158411920070648},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.31988632678985596}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2023.3288205","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3288205","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[{"id":"https://openalex.org/G2661465491","display_name":null,"funder_award_id":"2022JBZY019","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":77,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1567302070","https://openalex.org/W1834627138","https://openalex.org/W1861492603","https://openalex.org/W1962468782","https://openalex.org/W1984279162","https://openalex.org/W1999954155","https://openalex.org/W2007972815","https://openalex.org/W2031489346","https://openalex.org/W2066380143","https://openalex.org/W2095446616","https://openalex.org/W2108598243","https://openalex.org/W2164996823","https://openalex.org/W2171061940","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2267727210","https://openalex.org/W2395325225","https://openalex.org/W2410641892","https://openalex.org/W2413794162","https://openalex.org/W2463598282","https://openalex.org/W2518918709","https://openalex.org/W2521365688","https://openalex.org/W2626225338","https://openalex.org/W2736688973","https://openalex.org/W2738853914","https://openalex.org/W2788361849","https://openalex.org/W2808862089","https://openalex.org/W2890153145","https://openalex.org/W2895416001","https://openalex.org/W2909593838","https://openalex.org/W2913945456","https://openalex.org/W2932399282","https://openalex.org/W2963300078","https://openalex.org/W2963351448","https://openalex.org/W2963697527","https://openalex.org/W2963745697","https://openalex.org/W2963875806","https://openalex.org/W2982112268","https://openalex.org/W2995888011","https://openalex.org/W2997136715","https://openalex.org/W2998420437","https://openalex.org/W3013799809","https://openalex.org/W3027585699","https://openalex.org/W3034472074","https://openalex.org/W3034659318","https://openalex.org/W3034978279","https://openalex.org/W3035665101","https://openalex.org/W3046020157","https://openalex.org/W3080408769","https://openalex.org/W3096609285","https://openalex.org/W3099518117","https://openalex.org/W3102424508","https://openalex.org/W3109067582","https://openalex.org/W3154624119","https://openalex.org/W3165181705","https://openalex.org/W3167456680","https://openalex.org/W3171625335","https://openalex.org/W3174320978","https://openalex.org/W3174396085","https://openalex.org/W3174396556","https://openalex.org/W3176136157","https://openalex.org/W3179565650","https://openalex.org/W3189532445","https://openalex.org/W3192931333","https://openalex.org/W3202884348","https://openalex.org/W3205618423","https://openalex.org/W3211407538","https://openalex.org/W4212810184","https://openalex.org/W4283801767","https://openalex.org/W4293202648","https://openalex.org/W4295788787","https://openalex.org/W4312702383","https://openalex.org/W4366493098","https://openalex.org/W6630792627","https://openalex.org/W6739901393","https://openalex.org/W6784094891"],"related_works":["https://openalex.org/W4205762803","https://openalex.org/W2535856026","https://openalex.org/W2265065644","https://openalex.org/W2134699697","https://openalex.org/W3017188156","https://openalex.org/W2322875716","https://openalex.org/W2383516975","https://openalex.org/W2374878784","https://openalex.org/W2147679489","https://openalex.org/W2546503577"],"abstract_inverted_index":{"Graph":[0,15],"Matching":[1,16],"has":[2],"recently":[3],"emerged":[4],"as":[5,26,36,173],"an":[6,37,231,240],"attractive":[7],"technique":[8],"applied":[9],"to":[10,62,163,210,246],"various":[11,261],"computer":[12],"vision":[13],"tasks.":[14],"based":[17],"multi-label":[18,262],"image":[19,25,232,263],"classification,":[20],"in":[21,82,143,175,192],"particular,":[22],"treats":[23],"each":[24,190,224],"a":[27,87,144,198],"bag":[28],"of":[29,53,71,134,153,189,268],"instances":[30,75,170,216,229],"and":[31,51,68,76,130,146,171,179,183,217,219,233,251],"reformulates":[32],"the":[33,49,131,150,154,176,186,206,212,228,248,266],"classification":[34],"task":[35],"instance-label":[38,136,249],"matching":[39],"selection":[40],"problem,":[41],"achieving":[42],"state-of-the-art":[43],"results":[44],"on":[45,227,260],"diverse":[46],"benchmarks.":[47],"However,":[48],"generalization":[50],"scalability":[52],"such":[54],"learned":[55],"model":[56,161],"cannot":[57],"be":[58],"well":[59],"guaranteed":[60],"due":[61],"its":[63,193,202,234],"manually":[64],"predetermined":[65],"graph":[66],"structure":[67],"high-dimension":[69],"embedding":[70],"dense":[72],"connections":[73],"between":[74,215],"labels.":[77,238],"To":[78],"address":[79],"these":[80],"limitations,":[81],"this":[83],"work,":[84],"we":[85,167],"propose":[86],"novel":[88],"<inline-formula":[89,97,104,115],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[90,98,105,116],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[91,99,106,117],"<tex-math":[92,100,107,118],"notation=\"LaTeX\">${T}$":[93],"</tex-math></inline-formula>":[94,102,109,120],"ransformer":[95],"Driven":[96],"notation=\"LaTeX\">${M}$":[101],"atching":[103],"notation=\"LaTeX\">${S}$":[108],"election":[110],"framework":[111],"for":[112],"Multi-Label":[113],"Image":[114],"notation=\"LaTeX\">${C}$":[119],"lassification":[121],"(C-TMS),":[122],"where":[123],"instance":[124],"structural":[125],"relationships,":[126],"class-wise":[127],"global":[128],"dependencies,":[129],"co-occurrence":[132],"possibility":[133],"varying":[135],"assignments":[137,214],"are":[138],"simultaneously":[139],"taken":[140],"into":[141],"consideration":[142],"unified":[145],"adaptive":[147],"manner.":[148],"Moreover,":[149],"parallelization":[151],"capability":[152],"Transformer":[155],"enables":[156],"efficient":[157],"computation,":[158],"making":[159],"our":[160,269],"scalable":[162],"large-scale":[164],"datasets.":[165],"Specifically,":[166],"first":[168],"represent":[169],"labels":[172],"nodes":[174],"visual":[177],"space":[178,181],"label":[180,225],"respectively,":[182],"then":[184],"compute":[185],"hidden":[187],"representation":[188],"node":[191],"individual":[194],"space,":[195],"by":[196],"attending":[197],"self-attention":[199],"strategy":[200],"over":[201],"entire":[203],"neighborhood.":[204],"Subsequently,":[205],"cross-attention":[207],"is":[208,244],"adopted":[209],"excavate":[211],"correct":[213],"labels,":[218],"further":[220],"interprets":[221],"how":[222],"classifying":[223],"depends":[226],"within":[230],"interaction":[235],"with":[236],"other":[237],"Finally,":[239],"asymmetric":[241],"focal":[242],"loss":[243],"designed":[245],"optimize":[247],"correspondence,":[250],"read":[252],"out":[253],"image-level":[254],"category":[255],"confidences.":[256],"Extensive":[257],"experiments":[258],"conducted":[259],"datasets":[264],"demonstrate":[265],"superiority":[267],"proposed":[270],"method.":[271]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-18T07:39:51.176621","created_date":"2025-10-10T00:00:00"}